KSC 2019
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
SeHAGAN: GANÀ» ÀÌ¿ëÇÑ ¼øÂ÷Àû Àΰ£Çൿ »ý¼º |
¿µ¹®Á¦¸ñ(English Title) |
SeHAGAN: Sequential Human Actions Generation with GANs |
ÀúÀÚ(Author) |
¾ÆÁöÁî ½Ã¾ß¿¡ÇÁ
Á¶±Ù½Ä
AzizSiyaev
Geun-Sik Jo
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 46 NO. 02 PP. 0500 ~ 0502 (2019. 12) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
The Generative Adversarial Networks (GANs) have shown rapid development in different content-creation tasks. Among Them, the video generation gets its own attention due ti the development of various human centric applications like avatar animation. In this paper, we proposed a method to generate sequential human actions using a two-stage GANs pipeline. First, we produce pose skeleton with our Poses Generator, and then we textured them with a Frame Generator. Results showed that the proposed method SeHAGAN generates a plausible and high-quality video of human movements
|
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|